@Test
public void testColumnClustering() throws IOException {
Dataset<? extends Instance> dataset = FakeClustering.schoolData();
Props pref = new Props();
pref.put(AlgParams.LINKAGE, SingleLinkage.name);
pref.put(AlgParams.CLUSTERING_TYPE, ClusteringType.COLUMNS_CLUSTERING);
pref.put(PropType.PERFORMANCE, AlgParams.KEEP_PROXIMITY, true);
HierarchicalResult result = subject.hierarchy(dataset, pref);
Matrix similarityMatrix = result.getProximityMatrix();
assertNotNull(similarityMatrix);
assertEquals(similarityMatrix.rowsCount(), dataset.attributeCount());
assertEquals(similarityMatrix.columnsCount(), dataset.attributeCount());
result.getTreeData().print();
}
/**
* Sample covariance
*
* @param dataset
* @return
*/
protected double covariance(Dataset<E> dataset) {
Matrix m = dataset.asMatrix();
Matrix cov = new SymmetricMatrixDiag(m.columnsCount());
DenseVector mean = new DenseVector(dataset.attributeCount());
for (int i = 0; i < mean.size(); i++) {
mean.set(i, dataset.getAttribute(i).statistics(StatsNum.MEAN));
}
Vector v;
double res, sum = 0.0;
for (int i = 0; i < m.rowsCount(); i++) {
v = m.getRowVector(i).minus(mean);
res = v.dot(v);
sum += res;
}
return sum / (m.rowsCount() - 1);
/* for (int i = 0; i < m.columnsCount(); i++) { mean = dataset.getAttribute(i).statistics(StatsNum.AVG);
cov.set(i, i, dataset.getAttribute(i).statistics(StatsNum.VARIANCE));
for (int j = 0; j < i; j++) {
//cov.set(i, j, mean);
}
} */
// return cov;
}
@Override
public int size() {
switch (resultType) {
case COLUMNS_CLUSTERING:
return dataset.attributeCount();
case ROWS_CLUSTERING:
return dataset.size();
}
throw new RuntimeException("Don't know wether cluster rows or columns.");
}